Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure, and it does so extensively. It reveals that output is generated by Dead Cowboy's own code from validated fields, that content is third-party observational data of unverified accuracy, that it is never instruction, and it explains the CONFIRMED/UNCONFIRMED status semantics in detail. This goes far beyond a simple 'read' label and tells the agent exactly how much to trust and act on the result.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with the core action ('Read a coordinate') and then layers on necessary context about output generation and data reliability. Each sentence contributes meaningful information, though the CONFIRMED/UNCONFIRMED explanation is somewhat verbose. It is well-structured but not maximally concise.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has no output schema and no annotations, the description explains the nature of the return value (rendered summary), its epistemic status, and the meaning of confirmation statuses. It does not describe the exact output structure or error cases, but for a read tool with a schema that documents all parameters, it provides enough context for an agent to invoke it safely and interpret results. Slightly more detail on expected output fields would make it fully complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema already has 100% description coverage: coord is defined as a sha256 coordinate, kinds lists all enum values, and min_confidence is described as an optional 0.0-1.0 threshold. The description adds no additional parameter-specific meaning beyond the word 'coordinate.' With high schema coverage, a baseline of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with 'Read a coordinate,' a specific verb and resource, and further clarifies that it returns a rendered summary, not raw drops. This distinguishes it from sibling tools like derive (create), drop (write), and watch (monitor) without needing to name them explicitly. It falls short of 5 because it never explicitly contrasts with those siblings, leaving some differentiation to inference.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies when to use the tool — when you need to read a coordinate's summary — but gives no explicit guidance on choosing it over alternatives like watch or reputation. The detailed warnings about how to interpret output (treat as monitoring dashboard, not directive) are more about post-call interpretation than tool selection. Thus usage guidance is present but only implicit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.